DocsBlogPricingEnterpriseCareersResearch Grants
Log-inSign-up

CMMD Vision

ihja8w0lfciz8ywy5arq7vd7/cmmd
A better FID
Inference
Commercial use
PlaygroundAPI

About

Computes CMMD (CLIP Maximum Mean Discrepancy) given a path to a directory of images.

Args: hf_hub_path: HF dataset repository with an 'images' folder with images to compute embeds. reference_dataset: one of 'coco' or 'parti_full', or a path to a local directory containing the benchmark images. batch_size: Batch size to compute CLIP embeds at. Default:32

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("ihja8w0lfciz8ywy5arq7vd7/cmmd", {
  input: {
    hf_hub_path: "Icar/partiprompts_realvisxl4",
    reference_dataset: ""
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

3. Queue#

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("ihja8w0lfciz8ywy5arq7vd7/cmmd", {
  input: {
    hf_hub_path: "Icar/partiprompts_realvisxl4",
    reference_dataset: ""
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("ihja8w0lfciz8ywy5arq7vd7/cmmd", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("ihja8w0lfciz8ywy5arq7vd7/cmmd", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Read more about file handling in our file upload guide.

5. Schema#

Input#

hf_hub_path string* required

URL or HuggingFace ID of the HuggingFace dataset repo with the images whose CMMD is to be computed. Images must be under /images. Default value: undefined

reference_dataset string* required

One of 'coco', 'parti_full', 'parti_subset' or a HuggingFace ID of the HuggingFace dataset repository with the reference images. If the latter, images must be under /images. Default value: undefined

batch_size integer

Batch size to be used for computing the CLIP embeddings. The default value is 32. Default value: 32

{
  "hf_hub_path": "Icar/partiprompts_realvisxl4",
  "reference_dataset": "",
  "batch_size": 32
}

Output#

hf_hub_path string* required

URL or HuggingFace ID of the HuggingFace dataset repo for which the evaluation was done Default value: undefined

reference_dataset string* required

Reference dataset used in the evaluation. Default value: undefined

cmmd float* required

Computed CMMD (CLIP Maximum Mean Discrepancy) between the reference dataset and the generated images. Default value: undefined

{
  "hf_hub_path": "Icar/partiprompts_realvisxl4",
  "reference_dataset": ""
}

Other types#